arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.09387physics.plasm-phcs.LG
收藏

基于神经微分方程和强化学习的托卡马克下降阶段的主动破裂避免与轨迹设计

Active Disruption Avoidance and Trajectory Design for Tokamak Ramp-downs with Neural Differential Equations and Reinforcement Learning

Plasma Science and Fusion Center, Massachusetts Institute of Technology（麻省理工学院等离子体科学与聚变中心）；Laboratory for Information and Decision Systems, Massachusetts Institute of Technology（麻省理工学院信息与决策系统实验室）；OpenStar Technologies LLC.（OpenStar科技有限责任公司）

Allen M. Wang, Oswin So, Charles Dawson, Darren T. Garnier, Cristina Rea, Chuchu Fan

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本研究提出一种基于强化学习的策略，通过在混合物理与机器学习模型上训练，实现托卡马克下降阶段等离子体电流的安全降低与破裂避免，并利用约束条件化策略生成可离线验证的前馈轨迹库，为安全关键的燃烧等离子体场景提供了可行方案。

摘要：

托卡马克为实现聚变能提供了一条充满希望的途径，但等离子体破裂构成了重大的经济风险，促使破裂避免技术取得显著进展。本研究通过训练一种策略来安全降低等离子体电流，同时避免触及与破裂相关的多种物理量限制，从而开发了一种解决该问题的强化学习方法。策略训练环境是一个混合物理与机器学习模型，该模型基于SPARC初级参考放电（PRD）下降阶段的模拟进行训练，这是一个即将到来的燃烧等离子体场景，我们将其用作测试平台。为了解决物理不确定性和模型不准确的问题，在策略训练期间，模拟环境在GPU上进行了大规模并行化，并随机化了物理参数。随后，训练好的策略被成功迁移到更高保真度的模拟器中，在该模拟器中成功降低了等离子体电流，同时避免了用户指定的破裂限制。我们还通过证明约束条件化策略可作为轨迹设计助手，用于设计前馈轨迹库以处理不同的物理条件和用户设置，从而解决了安全关键性这一关键问题。由于轨迹库在离线状态下更具可解释性和可验证性，我们认为这种方法是在燃烧等离子体托卡马克这一安全关键背景下利用强化学习能力的充满希望的途径。最后，我们通过使用进化算法对物理不确定性具有鲁棒性的前馈轨迹进行优化，展示了该训练环境如何成为其他前馈优化方法的有用平台。

英文摘要：

The tokamak offers a promising path to fusion energy, but plasma disruptions pose a major economic risk, motivating considerable advances in disruption avoidance. This work develops a reinforcement learning approach to this problem by training a policy to safely ramp-down the plasma current while avoiding limits on a number of quantities correlated with disruptions. The policy training environment is a hybrid physics and machine learning model trained on simulations of the SPARC primary reference discharge (PRD) ramp-down, an upcoming burning plasma scenario which we use as a testbed. To address physics uncertainty and model inaccuracies, the simulation environment is massively parallelized on GPU with randomized physics parameters during policy training. The trained policy is then successfully transferred to a higher fidelity simulator where it successfully ramps down the plasma while avoiding user-specified disruptive limits. We also address the crucial issue of safety criticality by demonstrating that a constraint-conditioned policy can be used as a trajectory design assistant to design a library of feed-forward trajectories to handle different physics conditions and user settings. As a library of trajectories is more interpretable and verifiable offline, we argue such an approach is a promising path for leveraging the capabilities of reinforcement learning in the safety-critical context of burning plasma tokamaks. Finally, we demonstrate how the training environment can be a useful platform for other feed-forward optimization approaches by using an evolutionary algorithm to perform optimization of feed-forward trajectories that are robust to physics uncertainty

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑